Enable quantised model for TF Bonsai using quantizeBonsaiModels

tf/examples/Bonsai/README.md

@@ -46,6 +46,16 @@ Non-Zeros: 4156.0 Model Size: 31.703125 KB hasSparse: True
 
 usps10 directory will now have a consolidated results file called `TFBonsaiResults.txt` and a directory `TFBonsaiResults` with the corresponding models with each run of the code on the usps10 dataset
 
+## Byte Quantization(Q) for model compression
+If you wish to quantize the generated model to use byte quantized integers use `quantizeBonsaiModels.py`. Usage Instructions:
+
+```
+python quantizeBonsaiModels.py -h
+```
+
+This will generate quantized models with a suffix of `q` before every param stored in a new directory `QuantizedTFBonsaiModel` inside the model directory.
+One can use this model further on edge devices.
+
 
 Copyright (c) Microsoft Corporation. All rights reserved. 
 

tf/examples/Bonsai/helpermethods.py

@@ -106,6 +106,25 @@ def getArgs():
     return parser.parse_args()
 
 
+def getQuantArgs():
+    '''
+    Function to parse arguments for Model Quantisation
+    '''
+    parser = argparse.ArgumentParser(
+        description='Arguments for quantizing Fast models. ' +
+        'Works only for piece-wise linear non-linearities, ' +
+        'like relu, quantTanh, quantSigm (check rnn.py for the definitions)')
+    parser.add_argument('-dir', '--model-dir', required=True,
+                        help='model directory containing' +
+                        '*.npy weight files dumped from the trained model')
+    parser.add_argument('-m', '--max-val', type=checkIntNneg, default=127,
+                        help='this represents the maximum possible value ' +
+                        'in model, essentially the byte complexity, ' +
+                        '127=> 1 byte is default')
+
+    return parser.parse_args()
+
+
 def createTimeStampDir(dataDir):
     '''
     Creates a Directory with timestamp as it's name

tf/examples/Bonsai/quantizeBonsaiModels.py

@@ -0,0 +1,72 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT license.
+
+import helpermethods
+import os
+import numpy as np
+
+
+def min_max(A, name):
+    print(name + " has max: " + str(np.max(A)) + " min: " + str(np.min(A)))
+    return np.max([np.abs(np.max(A)), np.abs(np.min(A))])
+
+
+def quantizeFastModels(modelDir, maxValue=127, scalarScaleFactor=1000):
+    ls = os.listdir(modelDir)
+    paramNameList = []
+    paramWeightList = []
+    paramLimitList = []
+
+    for file in ls:
+        if file.endswith("npy"):
+            if file.startswith("mean") or file.startswith("std") or file.startswith("hyperParam"):
+                continue
+            else:
+                paramNameList.append(file)
+                temp = np.load(modelDir + "/" + file)
+                paramWeightList.append(temp)
+                paramLimitList.append(min_max(temp, file))
+
+    paramLimit = np.max(paramLimitList)
+
+    paramScaleFactor = np.round((2.0 * maxValue + 1.0) / (2.0 * paramLimit))
+
+    quantParamWeights = []
+    for param in paramWeightList:
+        temp = np.round(paramScaleFactor * param)
+        temp[temp[:] > maxValue] = maxValue
+        temp[temp[:] < -maxValue] = -1 * (maxValue + 1)
+
+        if maxValue <= 127:
+            temp = temp.astype('int8')
+        elif maxValue <= 32767:
+            temp = temp.astype('int16')
+        else:
+            temp = temp.astype('int32')
+
+        quantParamWeights.append(temp)
+
+    if os.path.isdir(modelDir + '/QuantizedTFBonsaiModel') is False:
+        try:
+            os.mkdir(modelDir + '/QuantizedTFBonsaiModel')
+            quantModelDir = modelDir + '/QuantizedTFBonsaiModel'
+        except OSError:
+            print("Creation of the directory %s failed" %
+                  modelDir + '/QuantizedFastModel')
+
+    np.save(quantModelDir + "/paramScaleFactor.npy",
+            paramScaleFactor.astype('int32'))
+
+    for i in range(len(paramNameList)):
+        np.save(quantModelDir + "/q" + paramNameList[i], quantParamWeights[i])
+
+    print("\n\nQuantized Model Dir: " + quantModelDir)
+
+
+def main():
+    args = helpermethods.getQuantArgs()
+    quantizeFastModels(args.model_dir, int(args.max_val))
+
+
+if __name__ == '__main__':
+    main()